Corn Kernel Counting via Image Threshold Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current manual methods for counting and characterizing corn kernels are prone to human error, leading to inaccuracy and potential fraud, as they lack verifiability and are not easily scalable for precise valuation of corn yields.
Innovation Solution
A digital image processing method that identifies optimal threshold values to generate binary images, allowing for the estimation of kernel counts by analyzing blob characteristics, such as fill factor, area, and separation, using regression decision trees for accurate counting and characterization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual counting methods are used, then operation simplicity is maintained, but measurement precision and reliability deteriorate due to human error and lack of verifiability
Solution Approach 1:
The patent replaces manual mechanical counting with an automated image processing system that captures images of corn ears and uses computer vision algorithms to detect, segment, and count kernels. This substitution eliminates human error while providing verifiable, precise measurements through digital image analysis and blob detection techniques.
Solution Approach 2:
The system creates a digital copy (image) of the physical corn ear and processes this copy to extract kernel count information. By working with the digital representation rather than the physical object, the system enables automated, repeatable, and verifiable counting without direct human intervention in the measurement process.
2Productivity
If automated image processing is implemented, then measurement precision and productivity improve, but device complexity and processing requirements increase
Solution Approach 1:
The system performs preliminary actions by capturing a complete image of the corn ear before counting begins. This pre-capture step allows all subsequent processing (thresholding, segmentation, blob detection, and counting) to be performed on the static digital image, enabling rapid processing without requiring complex real-time measurement equipment during the actual counting operation.
Solution Approach 2:
The image processing algorithm performs self-service by automatically detecting kernels, segmenting them from the background, and counting them without requiring manual calibration or adjustment for each corn ear. The system adapts to different images through automated threshold selection and blob analysis, reducing the need for complex user-configurable parameters while maintaining high processing speed.
Data Source
AI summary
Methods and apparatus are provided for identifying optimal threshold values to generate optimal binary images from a digital image. In one example, a method includes, for each of a plurality of candidate threshold values, processing an image using the candidate threshold value to create a first segmented image of a first plurality of blobs; for each of the plurality of candidate threshold values, calculating a threshold value evaluation metric as a count of qualifying blobs in the first plurality of blobs in the first segmented image, wherein the qualifying blobs have a fill factor exceeding a predefined fill factor and have an area within a predefined area range; identifying an optimal threshold value from the plurality of candidate threshold values for which the threshold value evaluation metric is maximized; and processing the image using the optimal threshold value to create a second segmented image of a second plurality of blobs.